Both KB and CL are improvements based on the q-EI method. is an approximate parallel strategy. Please point out if there is something wrong!
Ordinary q-EI:
Remember the black box function
Select q points in each round of iterations, and calculate the true response value of each point, that is
KB:
Remember the proxy model established by the current known data
Select q points in each iteration, and each point is no longer the real response value, but the value of the proxy model, that is,
CL:
Remember the known points , the current constant is L, where L can be
,
,
Select q points in each iteration, and each point is no longer the real response value, but the value of the proxy model, that is,